© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 164328
    Prev
    Next
    INDEX
    Explanations

    google

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Plain
    0.31
     Co
    0.30
     Que
    0.29
     ट्रॉ
    0.29
    😛
    0.28
    Plain
    0.27
     NEGLIGENCE
    0.27
     Cho
    0.27
     alkalmaz
    0.27
     pâ
    0.27
    POSITIVE LOGITS
    കം
    0.28
    숑
    0.27
     ضم
    0.27
    idio
    0.27
    公安
    0.27
     phrase
    0.26
    吲
    0.26
    ablanca
    0.26
     confocal
    0.26
     deserve
    0.26
    Activations Density 0.003%

    No Known Activations